Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dag
    -0.16
     sed
    -0.16
    ours
    -0.16
     bout
    -0.15
    our
    -0.14
    .Warn
    -0.14
    sed
    -0.14
     forever
    -0.14
    ondrous
    -0.14
     tầm
    -0.14
    POSITIVE LOGITS
    /Gate
    0.16
    ndern
    0.14
    hek
    0.14
    ofire
    0.14
    yw
    0.14
    eriod
    0.14
     Alg
    0.13
    ContextHolder
    0.13
    /vendors
    0.13
    ERIC
    0.13
    Act Density 0.010%

    No Known Activations